Title :
Nonlinear stabilization by receding-horizon neural regulators
Author :
Parisini, T. ; Sanguineti, M. ; Zoppoli, R.
Author_Institution :
Dept. of Electr., Electron. & Comput. Eng., Trieste Univ., Italy
Abstract :
A receding-horizon (RH) optimal control scheme for a discrete-time nonlinear dynamic system is presented. A nonquadratic cost function is considered and constraints are imposed on both the state and control vectors. A stabilizing regulator is derived by adding a proper terminal penalty function to the process cost. The control vector is generated by means of a feedback control law computed off-line instead of computing it online, as is done for existing RH regulators. The off-line computation is performed by approximating the RH regulator by a multilayer feedforward neural network. Bounds to this approximation are established. Algorithms are presented to determine some essential parameters for the design of the neural regulator, i.e., the parameters characterizing the terminal cost function and the number of neural units in the networks implementing the regulator. Simulation results show the effectiveness of the proposed approach
Keywords :
approximation theory; discrete time systems; feedback; feedforward neural nets; function approximation; neurocontrollers; nonlinear dynamical systems; optimal control; stability; approximation; control vector; discrete-time systems; feedback; multilayer feedforward neural network; nonlinear dynamic system; nonlinear stabilization; nonquadratic cost function; optimal control; receding-horizon neural control; state vector; terminal cost function; Algorithm design and analysis; Computer networks; Cost function; Feedback control; Feedforward neural networks; Multi-layer neural network; Neural networks; Nonlinear dynamical systems; Optimal control; Regulators;
Conference_Titel :
Decision and Control, 1995., Proceedings of the 34th IEEE Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-7803-2685-7
DOI :
10.1109/CDC.1995.478455
